Theory of recursive functions and effective computability
Theory of recursive functions and effective computability
On uniform learnability of language families
Information Processing Letters
Synthesizing enumeration techniques for language learning
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
Synthesizing inductive expertise
Information and Computation
Increasing the power of uniform inductive learners
Journal of Computer and System Sciences - Special issue on COLT 2002
Hi-index | 0.00 |
A classical learning problem in Inductive Inference consists of identifying each function of a given class of recursive functions from a finite number of its output values. Uniform learning is concerned with the design of single programs solving infinitely many classical learning problems. For that purpose the program reads a description of an identification problem and is supposed to construct a technique for solving the particular problem. As can be proved, uniform solvability of collections of solvable identification problems is rather influenced by the description of the problems than by the particular problems themselves. When prescribing a specific inference criterion (for example learning in the limit), a clever choice of descriptions allows uniform solvability of all solvable problems, whereas even the most simple classes of recursive functions are not uniformly learnable without restricting the set of possible descriptions. Furthermore the influence of the hypothesis spaces on uniform learnability is analysed.